Sharma Swati, Chuangsuwanich Thanadet, Tan Royston K Y, Prasad Shimna C, Tun Tin A, Perera Shamira A, Buist Martin L, Aung Tin, Nongpiur Monisha E, Girard Michaël J A
Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
Department of Ophthalmology, Emory University School of Medicine, Emory University.
ArXiv. 2025 Aug 19:arXiv:2508.14922v1.
To classify eyes as slow or fast glaucoma progressors in patients with primary angle closure glaucoma (PACG) using an integrated approach combining optic nerve head (ONH) structural features and sector-based visual field (VF) functional parameters.
Retrospective longitudinal study.
PACG patients from glaucoma clinics.
PACG patients with ≥5 reliable VF tests over ≥5 years were included. Progression was assessed in Zeiss Forum, with baseline VF within six months of OCT. Fast progression was VFI decline <-2.0% per year; slow progression ≥-2.0% per year. OCT volumes were AI-segmented to extract 31 ONH parameters. The Glaucoma Hemifield Test defined five regions per hemifield, aligned with RNFL distribution. Mean sensitivity per region was combined with structural parameters to train ML classifiers. Multiple models were tested, and SHAP identified key predictors.
Classification of slow versus fast progressors using combined structural and functional data.
We analyzed 451 eyes from 299 patients. Mean VFI progression was -0.92% per year; 369 eyes progressed slowly and 82 rapidly. The Random Forest model combining structural and functional features achieved the best performance (AUC = 0.87±0.02, 2000 Monte Carlo iterations). SHAP identified six key predictors: inferior MRW, inferior and inferior-temporal RNFL thickness, nasal-temporal LC curvature, superior nasal VF sensitivity, and inferior RNFL and GCL+IPL thickness. Models using only structural or functional features performed worse with AUC of 0.82±0.03 and 0.78±0.03, respectively.
Combining ONH structural and VF functional parameters significantly improves classification of progression risk in PACG. Inferior ONH features, MRW and RNFL thickness, were the most predictive, highlighting the critical role of ONH morphology in monitoring disease progression.
采用一种综合方法，结合视神经乳头（ONH）结构特征和基于象限的视野（VF）功能参数，对原发性闭角型青光眼（PACG）患者的眼睛进行慢速或快速青光眼进展分类。
回顾性纵向研究。
来自青光眼诊所的PACG患者。
纳入在≥5年期间进行了≥5次可靠VF检查的PACG患者。在蔡司论坛中评估进展情况，基线VF在OCT检查后6个月内。快速进展定义为每年视野指数（VFI）下降<-2.0%；缓慢进展为每年≥-2.0%。对OCT体积进行人工智能分割以提取31个ONH参数。青光眼半视野检查为每个半视野定义了五个区域，与视网膜神经纤维层（RNFL）分布对齐。每个区域的平均敏感度与结构参数相结合以训练机器学习分类器。测试了多个模型，SHAP确定了关键预测因素。
使用结构和功能数据组合对慢速与快速进展者进行分类。
我们分析了来自299名患者的451只眼睛。平均每年VFI进展为-0.92%；369只眼睛进展缓慢，82只眼睛进展迅速。结合结构和功能特征的随机森林模型表现最佳（曲线下面积[AUC]=0.87±0.02，2000次蒙特卡洛迭代）。SHAP确定了六个关键预测因素：下方平均视网膜神经纤维层宽度（MRW）、下方和颞下RNFL厚度、鼻颞侧视盘边缘曲率、鼻上象限VF敏感度以及下方RNFL和神经节细胞层+内丛状层（GCL+IPL）厚度。仅使用结构或功能特征的模型表现较差，AUC分别为0.82±0.03和0.78±0.03。
结合ONH结构和VF功能参数可显著改善PACG进展风险的分类。ONH下方特征（MRW和RNFL厚度）最具预测性，突出了ONH形态在监测疾病进展中的关键作用。
